Biomedical Imaging Group Rotterdam, Department of Radiology and Nuclear Medicine, Erasmus MC University Medical Centre Rotterdam, Rotterdam, the Netherlands.
Department of Radiology and Nuclear Medicine, Erasmus MC University Medical Centre Rotterdam, Rotterdam, the Netherlands.
Neuro Oncol. 2023 Feb 14;25(2):279-289. doi: 10.1093/neuonc/noac166.
Accurate characterization of glioma is crucial for clinical decision making. A delineation of the tumor is also desirable in the initial decision stages but is time-consuming. Previously, deep learning methods have been developed that can either non-invasively predict the genetic or histological features of glioma, or that can automatically delineate the tumor, but not both tasks at the same time. Here, we present our method that can predict the molecular subtype and grade, while simultaneously providing a delineation of the tumor.
We developed a single multi-task convolutional neural network that uses the full 3D, structural, preoperative MRI scans to predict the IDH mutation status, the 1p/19q co-deletion status, and the grade of a tumor, while simultaneously segmenting the tumor. We trained our method using a patient cohort containing 1508 glioma patients from 16 institutes. We tested our method on an independent dataset of 240 patients from 13 different institutes.
In the independent test set, we achieved an IDH-AUC of 0.90, an 1p/19q co-deletion AUC of 0.85, and a grade AUC of 0.81 (grade II/III/IV). For the tumor delineation, we achieved a mean whole tumor Dice score of 0.84.
We developed a method that non-invasively predicts multiple, clinically relevant features of glioma. Evaluation in an independent dataset shows that the method achieves a high performance and that it generalizes well to the broader clinical population. This first-of-its-kind method opens the door to more generalizable, instead of hyper-specialized, AI methods.
准确描述胶质瘤对于临床决策至关重要。在初始决策阶段，对肿瘤进行描绘也是可取的，但这很耗时。以前，已经开发出深度学习方法，可以无创地预测胶质瘤的遗传或组织学特征，或者可以自动描绘肿瘤，但不能同时完成这两个任务。在这里，我们提出了一种可以预测分子亚型和分级，同时提供肿瘤描绘的方法。
我们开发了一个单一的多任务卷积神经网络，该网络使用完整的 3D、结构、术前 MRI 扫描来预测 IDH 突变状态、1p/19q 共缺失状态以及肿瘤的分级，同时对肿瘤进行分割。我们使用来自 16 个机构的 1508 名胶质瘤患者的患者队列来训练我们的方法。我们在来自 13 个不同机构的 240 名患者的独立数据集上测试了我们的方法。
在独立测试集中，我们获得了 IDH-AUC 为 0.90、1p/19q 共缺失 AUC 为 0.85 和分级 AUC 为 0.81（分级 II/III/IV）。对于肿瘤描绘，我们获得了整个肿瘤的平均 Dice 分数为 0.84。
我们开发了一种无创预测胶质瘤的多个临床相关特征的方法。在独立数据集上的评估表明，该方法具有较高的性能，并且可以很好地推广到更广泛的临床人群。这种首创的方法为更具通用性而不是超专业化的人工智能方法打开了大门。
